| [Amazon Bedrock](https://aws.amazon.com/bedrock/) | Offers a variety of foundation models, including Claude, Jurassic-2, and others. **AWS environment variables must be set in advance, not configured through `goose configure`** | `AWS_PROFILE`, or `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_REGION` |
| [Amazon SageMaker TGI](https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html) | Run Text Generation Inference models through Amazon SageMaker endpoints. **AWS credentials must be configured in advance.** | `SAGEMAKER_ENDPOINT_NAME`, `AWS_REGION` (optional), `AWS_PROFILE` (optional) |
| [Anthropic](https://www.anthropic.com/) | Offers Claude, an advanced AI model for natural language tasks. | `ANTHROPIC_API_KEY`, `ANTHROPIC_HOST` (optional) |
| [Databricks](https://www.databricks.com/) | Unified data analytics and AI platform for building and deploying models. | `DATABRICKS_HOST`, `DATABRICKS_TOKEN` |
| [Docker Model Runner](https://docs.docker.com/ai/model-runner/) | Local models running in Docker Desktop or Docker CE with OpenAI-compatible API endpoints. **Because this provider runs locally, you must first [download a model](#local-llms).** | `OPENAI_HOST`, `OPENAI_BASE_PATH` |
| [GCP Vertex AI](https://cloud.google.com/vertex-ai) | Google Cloud's Vertex AI platform, supporting Gemini and Claude models. **Credentials must be [configured in advance](https://cloud.google.com/vertex-ai/docs/authentication).** | `GCP_PROJECT_ID`, `GCP_LOCATION` and optionally `GCP_MAX_RATE_LIMIT_RETRIES` (5), `GCP_MAX_OVERLOADED_RETRIES` (5), `GCP_INITIAL_RETRY_INTERVAL_MS` (5000), `GCP_BACKOFF_MULTIPLIER` (2.0), `GCP_MAX_RETRY_INTERVAL_MS` (320_000). |
| [GitHub Copilot](https://docs.github.com/en/copilot/using-github-copilot/ai-models) | Access to AI models from OpenAI, Anthropic, Google, and other providers through GitHub's Copilot infrastructure. **GitHub account with Copilot access required.** | No manual key. Must configure through the CLI using the GitHub authentication flow to enable both CLI and Desktop access. |
| [Ollama](https://ollama.com/) | Local model runner supporting Qwen, Llama, DeepSeek, and other open-source models. **Because this provider runs locally, you must first [download and run a model](#local-llms).** | `OLLAMA_HOST` |
| [Ramalama](https://ramalama.ai/) | Local model using native [OCI](https://opencontainers.org/) container runtimes, [CNCF](https://www.cncf.io/) tools, and supporting models as OCI artifacts. Ramalama API an compatible alternative to Ollama and can be used with the Goose Ollama provider. Supports Qwen, Llama, DeepSeek, and other open-source models. **Because this provider runs locally, you must first [download and run a model](#local-llms).** | `OLLAMA_HOST` |
| [OpenRouter](https://openrouter.ai/) | API gateway for unified access to various models with features like rate-limiting management. | `OPENROUTER_API_KEY` |
| [Snowflake](https://docs.snowflake.com/user-guide/snowflake-cortex/aisql#choosing-a-model) | Access the latest models using Snowflake Cortex services, including Claude models. **Requires a Snowflake account and programmatic access token (PAT)**. | `SNOWFLAKE_HOST`, `SNOWFLAKE_TOKEN` |
| [Tetrate Agent Router Service](https://router.tetrate.ai) | Unified API gateway for AI models including Claude, Gemini, GPT, open-weight models, and others. Supports PKCE authentication flow for secure API key generation. | `TETRATE_API_KEY`, `TETRATE_HOST` (optional) |
| [Venice AI](https://venice.ai/home) | Provides access to open source models like Llama, Mistral, and Qwen while prioritizing user privacy. **Requires an account and an [API key](https://docs.venice.ai/overview/guides/generating-api-key)**. | `VENICE_API_KEY`, `VENICE_HOST` (optional), `VENICE_BASE_PATH` (optional), `VENICE_MODELS_PATH` (optional) |
Goose also supports special "pass-through" providers that work with existing CLI tools, allowing you to use your subscriptions instead of paying per token:
| [Claude Code](https://www.anthropic.com/claude-code) (`claude-code`) | Uses Anthropic's Claude CLI tool with your Claude Code subscription. Provides access to Claude with 200K context limit. | Claude CLI installed and authenticated, active Claude Code subscription |
| [Cursor Agent](https://docs.cursor.com/en/cli/overview) (`cursor-agent`) | Uses Cursor's AI CLI tool with your Cursor subscription. Provides access to GPT-5, Claude 4, and other models through the cursor-agent command-line interface. | cursor-agent CLI installed and authenticated |
| [Gemini CLI](https://ai.google.dev/gemini-api/docs) (`gemini-cli`) | Uses Google's Gemini CLI tool with your Google AI subscription. Provides access to Gemini with 1M context limit. | Gemini CLI installed and authenticated |
:::tip CLI Providers
CLI providers are cost-effective alternatives that use your existing subscriptions. They work differently from API providers as they execute CLI commands and integrate with the tools' native capabilities. See the [CLI Providers guide](/docs/guides/cli-providers) for detailed setup instructions.
| `OPENAI_CUSTOM_HEADERS` | No | Additional headers to include in the request. Can be set via environment variable, configuration file, or CLI, in the format `HEADER_A=VALUE_A,HEADER_B=VALUE_B`. |
For enterprise deployments, you can pre-configure these values using environment variables or configuration files to ensure consistent governance across your organization.
Goose is a free and open source AI agent that you can start using right away, but not all supported [LLM Providers][providers] provide a free tier.
Below, we outline a couple of free options and how to get started with them.
:::warning Limitations
These free options are a great way to get started with Goose and explore its capabilities. However, you may need to upgrade your LLM for better performance.
Groq provides free access to open source models with high-speed inference. To use Groq with Goose, you need an API key from [Groq Console](https://console.groq.com/keys).
Groq offers several open source models that support tool calling:
- **moonshotai/kimi-k2-instruct** - Mixture-of-Experts model with 1 trillion parameters, optimized for agentic intelligence and tool use
- **qwen/qwen3-32b** - 32.8 billion parameter model with advanced reasoning and multilingual capabilities
- **gemma2-9b-it** - Google's Gemma 2 model with instruction tuning
- **llama-3.3-70b-versatile** - Meta's Llama 3.3 model for versatile applications
Google Gemini provides a free tier. To start using the Gemini API with Goose, you need an API Key from [Google AI studio](https://aistudio.google.com/app/apikey).
To set up Google Gemini with Goose, follow these steps:
Goose is a local AI agent, and by using a local LLM, you keep your data private, maintain full control over your environment, and can work entirely offline without relying on cloud access. However, please note that local LLMs require a bit more set up before you can use one of them with Goose.
Goose extensively uses tool calling, so models without it can only do chat completion. If using models without tool calling, all Goose [extensions must be disabled](/docs/getting-started/using-extensions#enablingdisabling-extensions).
2. In a terminal, run any Ollama [model supporting tool-calling](https://ollama.com/search?c=tools) or [GGUF format HuggingFace Model](https://huggingface.co/search/full-text?q=%22tools+support%22+%2B+%22gguf%22&type=model):
The `--runtime-args="--jinja"` flag is required for Ramalama to work with the Goose Ollama provider.
3. In a separate terminal window, configure with Goose:
```sh
goose configure
```
4. Choose to `Configure Providers`
```
┌ goose-configure
│
◆ What would you like to configure?
│ ● Configure Providers (Change provider or update credentials)
│ ○ Toggle Extensions
│ ○ Add Extension
└
```
5. Choose `Ollama` as the model provider since Ramalama is API compatible and can use the Goose Ollama provider
```
┌ goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◆ Which model provider should we use?
│ ○ Anthropic
│ ○ Databricks
│ ○ Google Gemini
│ ○ Groq
│ ● Ollama (Local open source models)
│ ○ OpenAI
│ ○ OpenRouter
└
```
6. Enter the host where your model is running
:::info Endpoint
For the Ollama provider, if you don't provide a host, we set it to `localhost:11434`. When constructing the URL, we preprend `http://` if the scheme is not `http` or `https`. Since Ramalama's default port to serve on is 8080, we set `OLLAMA_HOST=http://0.0.0.0:8080`
:::
```
┌ goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◇ Which model provider should we use?
│ Ollama
│
◆ Provider Ollama requires OLLAMA_HOST, please enter a value
│ http://0.0.0.0:8080
└
```
7. Enter the model you have running
```
┌ goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◇ Which model provider should we use?
│ Ollama
│
◇ Provider Ollama requires OLLAMA_HOST, please enter a value
│ http://0.0.0.0:8080
│
◇ Enter a model from that provider:
│ qwen2.5
│
◇ Welcome! You're all set to explore and utilize my capabilities. Let's get started on solving your problems together!
│
└ Configuration saved successfully
```
:::tip Context Length
If you notice that Goose is having trouble using extensions or is ignoring [.goosehints](/docs/guides/using-goosehints), it is likely that the model's default context length of 2048 tokens is too low. Use `ramalama serve` to set the `--ctx-size, -c` option to a [higher value](https://github.com/containers/ramalama/blob/main/docs/ramalama-serve.1.md#--ctx-size--c).
:::
</TabItem>
<TabItem value="deepseek" label="DeepSeek-R1">
The native `DeepSeek-r1` model doesn't support tool calling, however, we have a [custom model](https://ollama.com/michaelneale/deepseek-r1-goose) you can use with Goose.
:::warning
Note that this is a 70B model size and requires a powerful device to run smoothly.
2. In a terminal, run any [model supporting tool-calling](https://ollama.com/search?c=tools)
Example:
```sh
ollama run qwen2.5
```
3. In a separate terminal window, configure with Goose:
```sh
goose configure
```
4. Choose to `Configure Providers`
```
┌ goose-configure
│
◆ What would you like to configure?
│ ● Configure Providers (Change provider or update credentials)
│ ○ Toggle Extensions
│ ○ Add Extension
└
```
5. Choose `Ollama` as the model provider
```
┌ goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◆ Which model provider should we use?
│ ○ Anthropic
│ ○ Databricks
│ ○ Google Gemini
│ ○ Groq
│ ● Ollama (Local open source models)
│ ○ OpenAI
│ ○ OpenRouter
└
```
6. Enter the host where your model is running
:::info Endpoint
For Ollama, if you don't provide a host, we set it to `localhost:11434`.
When constructing the URL, we prepend `http://` if the scheme is not `http` or `https`.
If you're running Ollama on a different server, you'll have to set `OLLAMA_HOST=http://{host}:{port}`.
:::
```
┌ goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◇ Which model provider should we use?
│ Ollama
│
◆ Provider Ollama requires OLLAMA_HOST, please enter a value
│ http://localhost:11434
└
```
7. Enter the model you have running
```
┌ goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◇ Which model provider should we use?
│ Ollama
│
◇ Provider Ollama requires OLLAMA_HOST, please enter a value
│ http://localhost:11434
│
◇ Enter a model from that provider:
│ qwen2.5
│
◇ Welcome! You're all set to explore and utilize my capabilities. Let's get started on solving your problems together!
│
└ Configuration saved successfully
```
:::tip Context Length
If you notice that Goose is having trouble using extensions or is ignoring [.goosehints](/docs/guides/using-goosehints), it is likely that the model's default context length of 4096 tokens is too low. Set the `OLLAMA_CONTEXT_LENGTH` environment variable to a [higher value](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size).
:::
</TabItem>
</Tabs>
</TabItem>
<TabItem value="docker" label="Docker Model Runner" default>
2. [Enable Docker Model Runner](https://docs.docker.com/ai/model-runner/#enable-dmr-in-docker-desktop)
3. [Pull a model](https://docs.docker.com/ai/model-runner/#pull-a-model), for example, from Docker Hub [AI namespace](https://hub.docker.com/u/ai), [Unsloth](https://hub.docker.com/u/unsloth), or [from HuggingFace](https://www.docker.com/blog/docker-model-runner-on-hugging-face/)
If you have any questions or need help with a specific provider, feel free to reach out to us on [Discord](https://discord.gg/block-opensource) or on the [Goose repo](https://github.com/block/goose).
